Post Persona Alignment for Multi-Session Dialogue Generation

TL;DR

This paper introduces Post Persona Alignment (PPA), a two-stage method for improving long-term consistency, diversity, and personalization in multi-session dialogue generation by refining responses after initial generation.

Contribution

The paper presents a novel two-stage framework that reverses traditional retrieval methods, enhancing persona fidelity and conversational coherence in multi-session dialogues.

Findings

PPA outperforms prior methods in consistency and diversity.

PPA improves persona relevance in generated dialogues.

The approach enhances naturalness and personalization in multi-session interactions.

Abstract

Multi-session persona-based dialogue generation presents challenges in maintaining long-term consistency and generating diverse, personalized responses. While large language models (LLMs) excel in single-session dialogues, they struggle to preserve persona fidelity and conversational coherence across extended interactions. Existing methods typically retrieve persona information before response generation, which can constrain diversity and result in generic outputs. We propose Post Persona Alignment (PPA), a novel two-stage framework that reverses this process. PPA first generates a general response based solely on dialogue context, then retrieves relevant persona memories using the response as a query, and finally refines the response to align with the speaker's persona. This post-hoc alignment strategy promotes naturalness and diversity while preserving consistency and personalization. Experiments on multi-session LLM-generated dialogue data demonstrate that PPA significantly outperforms prior approaches in consistency, diversity, and persona relevance, offering a more flexible and effective paradigm for long-term personalized dialogue generation.